Temporal-difference Learning Using Distributed Error Signals

Abstract

A computational problem in biological reward-based learning is how credit assignment is performed in the nucleus accumbens (NAc). Much research suggests that NAc dopamine encodes temporal-difference (TD) errors for learning value predictions. However, dopamine is synchronously distributed in regionally homogeneous concentrations, which does not support explicit credit assignment (like used by backpropagation). It is unclear whether distributed errors alone are sufficient for synapses to make coordinated updates to learn complex, nonlinear reward-based learning tasks. We design a new deep Q-learning algorithm, Artificial Dopamine, to computationally demonstrate that synchronously distributed, per-layer TD errors may be sufficient to learn surprisingly complex RL tasks. We empirically evaluate our algorithm on MinAtar, the DeepMind Control Suite, and classic control tasks, and show it often achieves comparable performance to deep RL algorithms that use backpropagation.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyguan2024temporal

Related papers

• Learning Sparse Representations In Reinforcement Learning (2019)0.00
• Discerning Temporal Difference Learning (2023)0.00
• TD Or Not TD: Analyzing The Role Of Temporal Differencing In Deep Reinforcement Learning (2018)0.00
• DROP: Distributional And Regular Optimism And Pessimism For Reinforcement Learning (2024)0.00
• Gradient Temporal-difference Learning With Regularized Corrections (2020)0.00
• Simplifying Deep Temporal Difference Learning (2024)0.00
• Pseudo-quantized Actor-critic Algorithm For Robustness To Noisy Temporal Difference Error (2026)0.00
• An Improved Finite-time Analysis Of Temporal Difference Learning With Deep Neural Networks (2024)0.00